Search in sources :

Example 81 with TextField

use of edu.uci.ics.texera.api.field.TextField in project textdb by TextDB.

the class DictionaryMatcherTest method testSingleWordQueryInTextFieldUsingKeywordChinese.

/**
 * Scenario: verifies GetNextTuple of DictionaryMatcher and single word
 * queries in Text Field using KEYWORD OPERATOR in Chinese
 */
@Test
public void testSingleWordQueryInTextFieldUsingKeywordChinese() throws Exception {
    ArrayList<String> names = new ArrayList<String>(Arrays.asList("北京大学"));
    Dictionary dictionary = new Dictionary(names);
    // create a data tuple first
    List<Span> list = new ArrayList<Span>();
    Span span = new Span("description", 0, 4, "北京大学", "北京大学", 0);
    list.add(span);
    Attribute[] schemaAttributes = new Attribute[TestConstantsChinese.ATTRIBUTES_PEOPLE.length + 1];
    for (int count = 0; count < schemaAttributes.length - 1; count++) {
        schemaAttributes[count] = TestConstantsChinese.ATTRIBUTES_PEOPLE[count];
    }
    schemaAttributes[schemaAttributes.length - 1] = RESULTS_ATTRIBUTE;
    IField[] fields1 = { new StringField("无忌"), new StringField("长孙"), new IntegerField(46), new DoubleField(5.50), new DateField(new SimpleDateFormat("MM-dd-yyyy").parse("01-14-1970")), new TextField("北京大学电气工程学院"), new ListField<Span>(list) };
    IField[] fields2 = { new StringField("孔明"), new StringField("洛克贝尔"), new IntegerField(42), new DoubleField(5.99), new DateField(new SimpleDateFormat("MM-dd-yyyy").parse("01-13-1974")), new TextField("北京大学计算机学院"), new ListField<Span>(list) };
    Tuple tuple1 = new Tuple(new Schema(schemaAttributes), fields1);
    Tuple tuple2 = new Tuple(new Schema(schemaAttributes), fields2);
    List<Tuple> expectedResults = new ArrayList<Tuple>();
    expectedResults.add(tuple1);
    expectedResults.add(tuple2);
    List<String> attributeNames = Arrays.asList(TestConstantsChinese.FIRST_NAME, TestConstantsChinese.LAST_NAME, TestConstantsChinese.DESCRIPTION);
    List<Tuple> returnedResults = DictionaryMatcherTestHelper.getQueryResults(CHINESE_TABLE, dictionary, attributeNames, KeywordMatchingType.CONJUNCTION_INDEXBASED);
    boolean contains = TestUtils.equals(expectedResults, returnedResults);
    Assert.assertTrue(contains);
}
Also used : Dictionary(edu.uci.ics.texera.dataflow.dictionarymatcher.Dictionary) Attribute(edu.uci.ics.texera.api.schema.Attribute) Schema(edu.uci.ics.texera.api.schema.Schema) ArrayList(java.util.ArrayList) IntegerField(edu.uci.ics.texera.api.field.IntegerField) IField(edu.uci.ics.texera.api.field.IField) Span(edu.uci.ics.texera.api.span.Span) StringField(edu.uci.ics.texera.api.field.StringField) TextField(edu.uci.ics.texera.api.field.TextField) DateField(edu.uci.ics.texera.api.field.DateField) SimpleDateFormat(java.text.SimpleDateFormat) DoubleField(edu.uci.ics.texera.api.field.DoubleField) Tuple(edu.uci.ics.texera.api.tuple.Tuple) Test(org.junit.Test)

Example 82 with TextField

use of edu.uci.ics.texera.api.field.TextField in project textdb by TextDB.

the class DictionaryMatcherTest method testMatchingWithLimitOffset.

@Test
public void testMatchingWithLimitOffset() throws Exception {
    ArrayList<String> word = new ArrayList<String>(Arrays.asList("angry"));
    Dictionary dictionary = new Dictionary(word);
    Attribute[] schemaAttributes = new Attribute[TestConstants.ATTRIBUTES_PEOPLE.length + 1];
    for (int count = 0; count < schemaAttributes.length - 1; count++) {
        schemaAttributes[count] = TestConstants.ATTRIBUTES_PEOPLE[count];
    }
    schemaAttributes[schemaAttributes.length - 1] = RESULTS_ATTRIBUTE;
    Span span1 = new Span("description", 5, 10, "angry", "Angry");
    Span span2 = new Span("description", 6, 11, "angry", "Angry");
    Span span3 = new Span("description", 40, 45, "angry", "Angry");
    Span span4 = new Span("description", 6, 11, "angry", "angry");
    List<Span> list1 = new ArrayList<>();
    list1.add(span1);
    IField[] fields1 = { new StringField("bruce"), new StringField("john Lee"), new IntegerField(46), new DoubleField(5.50), new DateField(new SimpleDateFormat("MM-dd-yyyy").parse("01-14-1970")), new TextField("Tall Angry"), new ListField<>(list1) };
    List<Span> list2 = new ArrayList<>();
    list2.add(span2);
    IField[] fields2 = { new StringField("brad lie angelina"), new StringField("pitt"), new IntegerField(44), new DoubleField(6.10), new DateField(new SimpleDateFormat("MM-dd-yyyy").parse("01-12-1972")), new TextField("White Angry"), new ListField<>(list2) };
    List<Span> list3 = new ArrayList<>();
    list3.add(span3);
    IField[] fields3 = { new StringField("george lin lin"), new StringField("lin clooney"), new IntegerField(43), new DoubleField(6.06), new DateField(new SimpleDateFormat("MM-dd-yyyy").parse("01-13-1973")), new TextField("Lin Clooney is Short and lin clooney is Angry"), new ListField<>(list3) };
    List<Span> list4 = new ArrayList<>();
    list4.add(span4);
    IField[] fields4 = { new StringField("Mary brown"), new StringField("Lake Forest"), new IntegerField(42), new DoubleField(5.99), new DateField(new SimpleDateFormat("MM-dd-yyyy").parse("01-13-1974")), new TextField("Short angry"), new ListField<>(list4) };
    Tuple tuple1 = new Tuple(new Schema(schemaAttributes), fields1);
    Tuple tuple2 = new Tuple(new Schema(schemaAttributes), fields2);
    Tuple tuple3 = new Tuple(new Schema(schemaAttributes), fields3);
    Tuple tuple4 = new Tuple(new Schema(schemaAttributes), fields4);
    List<String> attributeNames = Arrays.asList(TestConstants.FIRST_NAME, TestConstants.LAST_NAME, TestConstants.DESCRIPTION);
    List<Tuple> expectedList = new ArrayList<>();
    List<Tuple> resultList = DictionaryMatcherTestHelper.getQueryResults(PEOPLE_TABLE, dictionary, attributeNames, KeywordMatchingType.PHRASE_INDEXBASED, 1, 3);
    expectedList.add(tuple1);
    expectedList.add(tuple2);
    expectedList.add(tuple3);
    expectedList.add(tuple4);
    Assert.assertEquals(expectedList.size(), 4);
    Assert.assertEquals(resultList.size(), 1);
    Assert.assertTrue(TestUtils.containsAll(expectedList, resultList));
}
Also used : Dictionary(edu.uci.ics.texera.dataflow.dictionarymatcher.Dictionary) Attribute(edu.uci.ics.texera.api.schema.Attribute) Schema(edu.uci.ics.texera.api.schema.Schema) ArrayList(java.util.ArrayList) IntegerField(edu.uci.ics.texera.api.field.IntegerField) IField(edu.uci.ics.texera.api.field.IField) Span(edu.uci.ics.texera.api.span.Span) StringField(edu.uci.ics.texera.api.field.StringField) TextField(edu.uci.ics.texera.api.field.TextField) DateField(edu.uci.ics.texera.api.field.DateField) SimpleDateFormat(java.text.SimpleDateFormat) DoubleField(edu.uci.ics.texera.api.field.DoubleField) Tuple(edu.uci.ics.texera.api.tuple.Tuple) Test(org.junit.Test)

Example 83 with TextField

use of edu.uci.ics.texera.api.field.TextField in project textdb by TextDB.

the class FuzzyTokenMatcherTest method TestFuzzyTokenMatcher2.

@Test
public void TestFuzzyTokenMatcher2() throws Exception {
    String query = "Twelve Angry Men";
    // The ratio of tokens that need to be matched
    double threshold = 0.5;
    ArrayList<String> attributeNames = new ArrayList<>();
    attributeNames.add(TestConstants.DESCRIPTION);
    Schema schema = new Schema.Builder().add(TestConstants.SCHEMA_PEOPLE).add(RESULTS_ATTR).build();
    List<Span> spanList1 = Arrays.asList(new Span(TestConstants.DESCRIPTION, 5, 10, "angry", "Angry", 1));
    IField[] fields1 = { new StringField("bruce"), new StringField("john Lee"), new IntegerField(46), new DoubleField(5.50), new DateField(new SimpleDateFormat("MM-dd-yyyy").parse("01-14-1970")), new TextField("Tall Angry"), new ListField<Span>(spanList1) };
    List<Span> spanList2 = Arrays.asList(new Span(TestConstants.DESCRIPTION, 6, 11, "angry", "Angry", 1));
    IField[] fields2 = { new StringField("brad lie angelina"), new StringField("pitt"), new IntegerField(44), new DoubleField(6.10), new DateField(new SimpleDateFormat("MM-dd-yyyy").parse("01-12-1972")), new TextField("White Angry"), new ListField<Span>(spanList2) };
    List<Span> spanList3 = Arrays.asList(new Span(TestConstants.DESCRIPTION, 40, 45, "angry", "Angry", 8));
    IField[] fields3 = { new StringField("george lin lin"), new StringField("lin clooney"), new IntegerField(43), new DoubleField(6.06), new DateField(new SimpleDateFormat("MM-dd-yyyy").parse("01-13-1973")), new TextField("Lin Clooney is Short and lin clooney is Angry"), new ListField<Span>(spanList3) };
    List<Span> spanList4 = Arrays.asList(new Span(TestConstants.DESCRIPTION, 6, 11, "angry", "angry", 1));
    IField[] fields4 = { new StringField("Mary brown"), new StringField("Lake Forest"), new IntegerField(42), new DoubleField(5.99), new DateField(new SimpleDateFormat("MM-dd-yyyy").parse("01-13-1974")), new TextField("Short angry"), new ListField<Span>(spanList4) };
    Tuple tuple1 = new Tuple(schema, fields1);
    Tuple tuple2 = new Tuple(schema, fields2);
    Tuple tuple3 = new Tuple(schema, fields3);
    Tuple tuple4 = new Tuple(schema, fields4);
    List<Tuple> expectedResultList = new ArrayList<>();
    expectedResultList.add(tuple1);
    expectedResultList.add(tuple2);
    expectedResultList.add(tuple3);
    expectedResultList.add(tuple4);
    List<Tuple> results = FuzzyTokenMatcherTestHelper.getQueryResults(PEOPLE_TABLE, query, threshold, attributeNames);
    boolean contains = TestUtils.equals(expectedResultList, results);
    Assert.assertTrue(contains);
}
Also used : Schema(edu.uci.ics.texera.api.schema.Schema) ArrayList(java.util.ArrayList) IntegerField(edu.uci.ics.texera.api.field.IntegerField) IField(edu.uci.ics.texera.api.field.IField) Span(edu.uci.ics.texera.api.span.Span) StringField(edu.uci.ics.texera.api.field.StringField) TextField(edu.uci.ics.texera.api.field.TextField) DateField(edu.uci.ics.texera.api.field.DateField) SimpleDateFormat(java.text.SimpleDateFormat) DoubleField(edu.uci.ics.texera.api.field.DoubleField) Tuple(edu.uci.ics.texera.api.tuple.Tuple) Test(org.junit.Test)

Example 84 with TextField

use of edu.uci.ics.texera.api.field.TextField in project textdb by TextDB.

the class JoinDistanceTest method testBothTheSpansAreSame.

// This case tests for the scenario when the spans to be joined are the same, i.e. both the keywords
// are same.
// e.g.
// [<11, 18>]
// [<11, 18>]
// threshold = 20 (can be any non-negative number)
// [ ]
// [ ]
// Test result: Join should return same span and key and the value in span
// should be the same.
// [<11, 18>]
@Test
public void testBothTheSpansAreSame() throws Exception {
    JoinTestHelper.insertToTable(BOOK_TABLE, JoinTestConstants.bookGroup1.get(0));
    KeywordMatcherSourceOperator keywordSourceOuter = JoinTestHelper.getKeywordSource(BOOK_TABLE, "special", conjunction);
    KeywordMatcherSourceOperator keywordSourceInner = JoinTestHelper.getKeywordSource(BOOK_TABLE, "special", conjunction);
    List<Tuple> resultList = JoinTestHelper.getJoinDistanceResults(keywordSourceInner, keywordSourceOuter, new JoinDistancePredicate(JoinTestConstants.REVIEW, 20), Integer.MAX_VALUE, 0);
    Schema resultSchema = new Schema.Builder().add(JoinTestConstants.BOOK_SCHEMA).add(SchemaConstants.SPAN_LIST_ATTRIBUTE).build();
    List<Span> spanList = new ArrayList<>();
    Span span1 = new Span(JoinTestConstants.REVIEW, 11, 18, "special_special", "special");
    spanList.add(span1);
    IField[] book1 = { new IntegerField(52), new StringField("Mary Roach"), new StringField("Grunt: The Curious Science of Humans at War"), new IntegerField(288), new TextField("It takes a special kind " + "of writer to make topics ranging from death to our " + "gastrointestinal tract interesting (sometimes " + "hilariously so), and pop science writer Mary Roach is " + "always up to the task."), new ListField<>(spanList) };
    Tuple expectedTuple = new Tuple(resultSchema, book1);
    List<Tuple> expectedResult = new ArrayList<>();
    expectedResult.add(expectedTuple);
    Assert.assertEquals(1, resultList.size());
    Assert.assertTrue(TestUtils.equals(expectedResult, resultList));
}
Also used : Schema(edu.uci.ics.texera.api.schema.Schema) ArrayList(java.util.ArrayList) IntegerField(edu.uci.ics.texera.api.field.IntegerField) IField(edu.uci.ics.texera.api.field.IField) JoinDistancePredicate(edu.uci.ics.texera.dataflow.join.JoinDistancePredicate) Span(edu.uci.ics.texera.api.span.Span) KeywordMatcherSourceOperator(edu.uci.ics.texera.dataflow.keywordmatcher.KeywordMatcherSourceOperator) StringField(edu.uci.ics.texera.api.field.StringField) TextField(edu.uci.ics.texera.api.field.TextField) Tuple(edu.uci.ics.texera.api.tuple.Tuple) Test(org.junit.Test)

Example 85 with TextField

use of edu.uci.ics.texera.api.field.TextField in project textdb by TextDB.

the class JoinDistanceTest method testForLimitWhenLimitIsGreaterThanActualNumberOfResults.

/*
     * This case tests for the scenario when limit is some integer greater than
     * 0 and greater than the actual number of results and offset is 0 and join
     * is performed.
     * Test result: A list of tuples with number of tuples equal to the maximum
     * number of tuples operator can generate (which is lesser than limit.)
     */
@Test
public void testForLimitWhenLimitIsGreaterThanActualNumberOfResults() throws Exception {
    List<Tuple> tuples = JoinTestConstants.bookGroup1.subList(1, 5);
    JoinTestHelper.insertToTable(BOOK_TABLE, tuples);
    KeywordMatcherSourceOperator keywordSourceOuter = JoinTestHelper.getKeywordSource(BOOK_TABLE, "typical", conjunction);
    KeywordMatcherSourceOperator keywordSourceInner = JoinTestHelper.getKeywordSource(BOOK_TABLE, "actually", conjunction);
    List<Tuple> resultList = JoinTestHelper.getJoinDistanceResults(keywordSourceInner, keywordSourceOuter, new JoinDistancePredicate(JoinTestConstants.REVIEW, 90), 10, 0);
    Schema resultSchema = new Schema.Builder().add(JoinTestConstants.BOOK_SCHEMA).add(SchemaConstants.SPAN_LIST_ATTRIBUTE).build();
    List<Span> spanList = new ArrayList<>();
    Span span1 = new Span(JoinTestConstants.REVIEW, 28, 119, "typical_actually", "typical review. " + "This is a test. A book review test. " + "A test to test queries without actually");
    spanList.add(span1);
    Span span2 = new Span(JoinTestConstants.REVIEW, 186, 234, "typical_actually", "actually a review " + "even if it is not your typical");
    spanList.add(span2);
    IField[] book1 = { new IntegerField(51), new StringField("author unknown"), new StringField("typical"), new IntegerField(300), new TextField("Review of a Book. This is a typical " + "review. This is a test. A book review " + "test. A test to test queries without " + "actually using actual review. From " + "here onwards, we can pretend this to " + "be actually a review even if it is not " + "your typical book review."), new ListField<>(spanList) };
    IField[] book2 = { new IntegerField(53), new StringField("Noah Hawley"), new StringField("Before the Fall"), new IntegerField(400), new TextField("Review of a Book. This is a typical " + "review. This is a test. A book review " + "test. A test to test queries without " + "actually using actual review. From " + "here onwards, we can pretend this to " + "be actually a review even if it is not " + "your typical book review."), new ListField<>(spanList) };
    IField[] book3 = { new IntegerField(54), new StringField("Andria Williams"), new StringField("The Longest Night: A Novel"), new IntegerField(400), new TextField("Review of a Book. This is a typical " + "review. This is a test. A book review " + "test. A test to test queries without " + "actually using actual review. From " + "here onwards, we can pretend this to " + "be actually a review even if it is not " + "your typical book review."), new ListField<>(spanList) };
    IField[] book4 = { new IntegerField(55), new StringField("Matti Friedman"), new StringField("Pumpkinflowers: A Soldier's " + "Story"), new IntegerField(256), new TextField("Review of a Book. This is a typical " + "review. This is a test. A book review " + "test. A test to test queries without " + "actually using actual review. From " + "here onwards, we can pretend this to " + "be actually a review even if it is not " + "your typical book review."), new ListField<>(spanList) };
    Tuple expectedTuple1 = new Tuple(resultSchema, book1);
    Tuple expectedTuple2 = new Tuple(resultSchema, book2);
    Tuple expectedTuple3 = new Tuple(resultSchema, book3);
    Tuple expectedTuple4 = new Tuple(resultSchema, book4);
    List<Tuple> expectedResult = new ArrayList<>(5);
    expectedResult.add(expectedTuple1);
    expectedResult.add(expectedTuple2);
    expectedResult.add(expectedTuple3);
    expectedResult.add(expectedTuple4);
    Assert.assertEquals(4, resultList.size());
    Assert.assertTrue(TestUtils.equals(expectedResult, resultList));
}
Also used : Schema(edu.uci.ics.texera.api.schema.Schema) ArrayList(java.util.ArrayList) IntegerField(edu.uci.ics.texera.api.field.IntegerField) IField(edu.uci.ics.texera.api.field.IField) JoinDistancePredicate(edu.uci.ics.texera.dataflow.join.JoinDistancePredicate) Span(edu.uci.ics.texera.api.span.Span) KeywordMatcherSourceOperator(edu.uci.ics.texera.dataflow.keywordmatcher.KeywordMatcherSourceOperator) StringField(edu.uci.ics.texera.api.field.StringField) TextField(edu.uci.ics.texera.api.field.TextField) Tuple(edu.uci.ics.texera.api.tuple.Tuple) Test(org.junit.Test)

Aggregations

TextField (edu.uci.ics.texera.api.field.TextField)115 IField (edu.uci.ics.texera.api.field.IField)99 Tuple (edu.uci.ics.texera.api.tuple.Tuple)89 ArrayList (java.util.ArrayList)84 IntegerField (edu.uci.ics.texera.api.field.IntegerField)78 StringField (edu.uci.ics.texera.api.field.StringField)78 Span (edu.uci.ics.texera.api.span.Span)78 Schema (edu.uci.ics.texera.api.schema.Schema)77 Test (org.junit.Test)76 DoubleField (edu.uci.ics.texera.api.field.DoubleField)63 DateField (edu.uci.ics.texera.api.field.DateField)58 Attribute (edu.uci.ics.texera.api.schema.Attribute)56 SimpleDateFormat (java.text.SimpleDateFormat)56 Dictionary (edu.uci.ics.texera.dataflow.dictionarymatcher.Dictionary)29 ListField (edu.uci.ics.texera.api.field.ListField)11 JoinDistancePredicate (edu.uci.ics.texera.dataflow.join.JoinDistancePredicate)9 KeywordMatcherSourceOperator (edu.uci.ics.texera.dataflow.keywordmatcher.KeywordMatcherSourceOperator)9 JsonNode (com.fasterxml.jackson.databind.JsonNode)5 IOperator (edu.uci.ics.texera.api.dataflow.IOperator)5 ObjectMapper (com.fasterxml.jackson.databind.ObjectMapper)4